The effects of parallel processing on update response time in distributed database design

Network latency and local update are the most significant components of update response time in a distributed database system. Effectively designed distributed database systems can take advantage of parallel processing to minimize this time. We present a design approach to response time minimization for update transactions in a distributed database. Response time is calculated as the sum of local processing and communication, including transmit time, queuing delays, and network latency. We demonstrate that parallelism has significant impacts on the efficiency of data allocation strategies in the design of high transaction-volume distributed databases.

[1]  Maria E. Orlowska,et al.  On data allocation with minimum overall communication costs in distributed database design , 1993, Proceedings of ICCI'93: 5th International Conference on Computing and Information.

[2]  Robert T. Braden,et al.  Extending TCP for Transactions - Concepts , 1992, RFC.

[3]  Sangkyu Rho,et al.  Designing Distributed Database Systems for Efficient Operation , 1995, ICIS.

[4]  Jesper M. Johansson.  On the impact of network latency on distributed systems design , 2000, Inf. Technol. Manag..

[5]  Waqar Hasan,et al.  Optimization of SQL Queries for Parallel Machines , 1996, Lecture Notes in Computer Science.

[6]  Sangkyu Rho,et al.  Allocating Data and Operations to Nodes in Distributed Database Design , 1995, IEEE Trans. Knowl. Data Eng..

[7]  Amitava Mukherjee,et al.  An Optimal File Allocation Policy in a Networked Database Management System , 1994, Int. J. Netw. Manag..

[8]  C. V. Ramamoorthy,et al.  Knowledge and Data Engineering , 1989, IEEE Trans. Knowl. Data Eng..

[9]  Jim Gray,et al.  The cost of messages , 1988, PODC '88.

[10]  Sudha Ram,et al.  Database Allocation in a Distributed Environment: Incorporating a Concurrency Control Mechanism and Queuing Costs , 1994 .

[11]  Sangkyu Rho.  Distributed database design: allocation of data and operations to nodes in distributed database systems , 1995 .

[12]  Jesper M. Johansson,et al.  Impact of high-speed wide area network response time dynamics on distributed database design , 1999 .

[13]  Alan R. Hevner,et al.  An Iterative Method for Distributed Database Optimization , 1996, Data Knowl. Eng..

[14]  Peter M G Apers,et al.  Data allocation in distributed database systems , 1988, TODS.

[15]  Philip S. Yu,et al.  On Optimal Site Assignment for Relations in the Distributed Database Environment , 1989, IEEE Trans. Software Eng..